collaborators

8 papers

cs.AI2026

One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA

Zhi Zheng, Ziqiao Meng, Hao Luan +2

External memory effectively grounds large language models (LLMs) and vision-language models (VLMs)-based question answering (QA) in relevant multimodal evidence. However, existing…

cs.LG2026

Rethinking the Divergence Regularization in LLM RL

Jiarui Yao, Xiangxin Zhou, Penghui Qi +3

Reinforcement learning (RL) has become a key component of post-training large language models (LLMs). In practice, LLM RL is often off-policy because of training-inference mismatch…

cs.CL2026

From Backward Spreading to Forward Replay: Revisiting Target Construction in LLM Parameter Editing

Wei Liu, Hongkai Liu, Zhiying Deng +2

LLM parameter editing methods commonly rely on computing an ideal target hidden-state at a target layer (referred as anchor point) and distributing the target vector to multiple pr…

cs.CV2026

Can Vision-Language Models Solve the Shell Game?

Tiedong Liu, Wee Sun Lee

Visual entity tracking is an innate cognitive ability in humans, yet it remains a critical bottleneck for Vision-Language Models (VLMs). This deficit is often obscured in existing…

cs.LG2026

GEM: A Gym for Agentic LLMs

Zichen Liu, Anya Sims, Keyu Duan +16

The training paradigm for large language models (LLMs) is moving from static datasets to experience-based learning, where agents acquire skills via interacting with complex environ…

cs.AI2026

Are We Evaluating the Edit Locality of LLM Model Editing Properly?

Wei Liu, Haomei Xu, Hongkai Liu +5

Model editing has recently emerged as a popular paradigm for efficiently updating knowledge in LLMs. A central desideratum of updating knowledge is to balance editing efficacy, i.e…